CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

credentials

Instructions for handling API keys and credentials safely, verifying their presence, and prompting the user to add them if missing using a safe protocol.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/credentials/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with copy-paste-ready commands and a clear verify-or-prompt workflow, well-organized into sections; its main weakness is repeated CRITICAL warnings that pad the text.

Suggestions

Consolidate the duplicated no-leak and 'do not conclude the turn' warnings into a single CRITICAL callout to remove redundancy and tighten conciseness.

Make the verify→prompt→run sequence an explicit numbered checklist so the workflow checkpoints read at a glance.

Consider folding the repeated placeholder-substitution instructions into one clearly marked step to reduce restatement.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but repeated CRITICAL admonitions and duplicated phrasing (e.g., 'do not conclude the turn by simply stating the key is missing' appears twice, and the no-leak warning is restated several times) could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean 4.

3 / 5

Actionability

Provides copy-paste-ready executable commands — `grep -sq "^CREDENTIAL_NAME=" ~/.env` and the `printf ... read -s ...` template — with placeholder replacement documented explicitly, covering the common verification and prompt cases, matching the 'fully executable; copy-paste ready' anchor.

5 / 5

Workflow Clarity

Clear sequence (verify presence first → proceed, or stop and generate a prompt command → user adds → run script) with an explicit validation checkpoint (the grep exit-code check) and an error-recovery feedback loop, but a couple of minor validation gaps keep it just below the fully-checklisted 5; this is not a destructive/batch operation so the 3-cap does not apply.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, has no external references, and is organized into well-signaled sections (Safe Verification, Prompting the User, Running scripts), so per the simple-skills scoring note it qualifies for 5 with well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states what the skill does with several concrete actions, but omits an explicit 'when to use it' trigger clause, capping completeness, and has decent but incomplete natural-keyword coverage.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g., 'Use when a skill requires an API key or credential and you need to verify or prompt for it without leaking the value').

Broaden trigger terms to include common synonyms users say, such as 'secrets', 'tokens', and 'API key'.

Tighten 'handling API keys and credentials safely' into a more specific action verb set to push specificity toward 5.

DimensionReasoningScore

Specificity

Names the domain (API keys/credentials) and several concrete actions — 'handling... safely', 'verifying their presence', and 'prompting the user to add them if missing' — with only minor gaps in coverage, fitting the 'lists several specific actions' anchor better than the '1-2 concrete actions' anchor at 3.

4 / 5

Completeness

The 'what' is clear (handling/verifying/prompting for credentials), but there is no explicit 'Use when...' trigger clause — the 'when' is only weakly implied — so per the missing-trigger-clause cap it cannot exceed 3.

3 / 5

Trigger Term Quality

Includes the natural terms 'API keys' and 'credentials' that users would say, but misses common synonyms and variations (e.g., 'secrets', 'tokens', 'API key' singular), matching the 'some relevant keywords but missing common variations' anchor rather than the fuller coverage at 4.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (a safe credentials-handling protocol) that is mostly distinct from other skills, with only minor overlap risk against closely related secrets-management skills; it does not quite reach the minimal-conflict, distinct-trigger clarity of a 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

google-deepmind/science-skills

Path

skills/credentials/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.